ArcFace: Additive Angular Margin Loss for Deep Face Recognition
Citations
25 citations
25 citations
25 citations
25 citations
Cites background from "ArcFace: Additive Angular Margin Lo..."
...This is a classical problem in metric learning [13], [37]....
[...]
25 citations
Cites background or methods from "ArcFace: Additive Angular Margin Lo..."
...fication accuracy on best threshold. AUC is the area under the ROC curve. (a) without face (b) with face Figure 8: A schematic to indicate face and cartoon feature position in the feature space. 2018; Deng et al. 2019). In this part, we try to accomplish this goal by using dataset fusion methods. The motivation of dataset fusion is that person faces and cartoon faces have similar shapes. Therefore, the trained cart...
[...]
... iCartoonFace dataset. Loss Functions Decision Boundaries SoftMax (W 1 W 2)x+b 1 b 2 = 0 SphereFace(Liu et al. 2017) kxk(cos(m 1) cos 2) = 0 CosFace(Wang et al. 2018) s(cos 1 m cos 2) = 0 ArcFace(Deng et al. 2019) s(cos( 1 +m) cos 2) = 0 Table 1: Decision boundaries of different loss functions. imize inter-class distance and minimize intra-class distance by loss functions. SphereFace(Liu et al. 2017) propose...
[...]
...l. 2008) and MegaFace(Kemelmacher-Shlizerman et al. 2016), provide evaluation protocols and rankings. Rich publicly available face data have greatly promoted the research of face recognition. ArcFace(Deng et al. 2019) reached a precision of 99.83% on LFW benchmark, which had surpassed the human performance. The best results on MegaFace has also reached 99.39%. However, in the field of cartoon face recognition, such...
[...]
...j kW j k ;x i= x i kx i k ;cos( j) = WTx i: (6) The experimental results is shown in Figure 12 and table 4. It can be observed that SphereFace(Liu et al. 2017), CosFace(Wang et al. 2018) and ArcFace(Deng et al. 2019) loss performs better than SoftMax loss. Compared to SoftMax, SphereFace, CosFace and ArcFace expand inter-class angular margin to expand inter-class distance and reduce intraclass distance. CosFace h...
[...]
...for all algorithms as shown in figure 7(c). Loss Functions We also compared several loss functions designed for face recognition, i.e.SphereFace(Liu et al. 2017), CosFace(Wang et al. 2018) and ArcFace(Deng et al. 2019). The SphereFace can be written as L sphere= 1 N X i log( ekxik (yi;i) ekxik (yi;i)) + P j6= yi ekxikcos(j;i ) (1) Loss SoftMax SphereFace CosFace ArcFace Rank-1(%) 57.07 57.77 68.91 66.64 Best Acc...
[...]
References
123,388 citations
33,597 citations
30,843 citations
13,268 citations
10,447 citations